Kimi K2.7 Code — API Pricing & Benchmarks
Kimi K2.7 Code is Moonshot AI's mid reasoning model, released in 2026-06. The API costs $0.95 per 1M input tokens and $4.00 per 1M output tokens ($1.71 blended at a 3:1 ratio), with cached input at $0.19. It supports a 262K-token context window. On the independently measured Artificial Analysis Intelligence Index it scores 43, ranking #37 of 68 models tracked on this site, with a median output speed of 39 tokens/sec.
Explore provider routes and additional benchmark sources for Kimi K2.7 Code
| Provider | Moonshot AI |
| Input price / 1M tokens | $0.95 |
| Output price / 1M tokens | $4.00 |
| Cached input / 1M tokens | $0.19 |
| Blended price (3:1) | $1.71 |
| Context window | 262K |
| Max output tokens | 33K |
| Knowledge cutoff | — |
| License | open weights |
| Input modalities | T+I+V |
| Output speed (tok/s) | 39 |
| Released | 2026-06 |
| Artificial Analysis Intelligence Index | 43 |
| GPQA Diamond | 89.6% |
| Humanity's Last Exam | 35% |
Where Kimi K2.7 Code fits
On a blended 3:1 basis Kimi K2.7 Code costs $1.71 per 1M tokens, cheaper than 49% of the 80 priced models in this index. It sits in the mid-tier bracket where most production chat, RAG and summarization workloads run: meaningfully cheaper than flagships while keeping most of their capability. Measured output speed of 39 tokens/sec is below the index median of 104 — typical of reasoning-heavy models, and worth checking against interactive latency budgets. The weights are open, so it can be self-hosted for data-residency or cost reasons instead of consumed via API. Cached input is priced at $0.19 (80% below standard input), which rewards prompt structures with long stable prefixes — see our caching guide.
Price history
| Period | Input $/1M | Output $/1M | Cached $/1M |
|---|---|---|---|
| 2026-07-18 → current | $0.95 | $4.00 | $0.19 |
No list-price changes recorded since tracking began. Full dataset: price-history.json (CC BY 4.0).
Alternatives at a similar price
- Kimi K2.6 (Moonshot AI) — $1.71/1M blended, AA Index 45.1
- GPT-5.4 mini (OpenAI) — $1.69/1M blended, AA Index 40.9
- Grok 4.3 (xAI) — $1.56/1M blended, AA Index 37.9
- Grok 4.20 (xAI) — $1.56/1M blended
About Moonshot AI
Moonshot AI builds the Kimi models. Kimi K3 is currently the strongest open-weights model in this index, benchmarking alongside proprietary flagships while remaining self-hostable.